Lifelong Learning of Large Language Model based Agents: A Roadmap
Zheng, Junhao Shi, Chengming Cai, Xidi Li, Qiuke Zhang, Duzhen Li, Chenxing Yu, Dong Ma, Qianli
Zheng, Junhao
Shi, Chengming
Cai, Xidi
Li, Qiuke
Zhang, Duzhen
Li, Chenxing
Yu, Dong
Ma, Qianli
Supervisor
Department
Machine Learning
Embargo End Date
Type
Journal article
Date
2026
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Lifelong learning, also known as continual or incremental learning, is a crucial component for advancing Artificial General Intelligence (AGI) by enabling systems to continuously adapt in dynamic environments. While large language models (LLMs) have demonstrated impressive capabilities in natural language processing, existing LLM agents are typically designed for static systems and lack the ability to adapt over time in response to new challenges. This survey is the first to systematically summarize the potential techniques for incorporating lifelong learning into LLM-based agents. We categorize the core components of these agents into three modules: the perception module for multimodal input integration, the memory module for storing and retrieving evolving knowledge, and the action module for grounded interactions with the dynamic environment. We highlight how these pillars collectively enable continuous adaptation, mitigate catastrophic forgetting, and improve long-term performance. This survey provides a roadmap for researchers and practitioners working to develop lifelong learning capabilities in LLM agents, offering insights into emerging trends, evaluation metrics, and application scenarios.
Citation
J. Zheng et al., "Lifelong Learning of Large Language Model based Agents: A Roadmap," in IEEE Transactions on Pattern Analysis and Machine Intelligence, doi: 10.1109/TPAMI.2025.3650546
Source
IEEE Transactions on Pattern Analysis and Machine Intelligence
Conference
Keywords
AGI, AI Agent, Continual Learning, Incremental Learning, Large Language Model, Lifelong Learning
Subjects
Source
Publisher
IEEE